Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4119 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4253. Min Range: -6.4253
Max Act: 6.4253. Min Act: -0.1700
Data Index: 5666954 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4253. Min Range: -6.4253
Max Act: 6.1441. Min Act: -0.1700
Data Index: 1186335 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4253. Min Range: -6.4253
Max Act: 6.0503. Min Act: -0.1700
Data Index: 470914 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4253. Min Range: -6.4253
Max Act: 6.0191. Min Act: -0.1700
Data Index: 4847523 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4253. Min Range: -6.4253
Max Act: 5.9566. Min Act: -0.1700
Data Index: 278323 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4253. Min Range: -6.4253
Max Act: 5.9566. Min Act: -0.1700
Data Index: 7270855 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4253. Min Range: -6.4253
Max Act: 5.9566. Min Act: -0.1700
Data Index: 8121127 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4253. Min Range: -6.4253
Max Act: 5.9566. Min Act: -0.1700
Data Index: 6961124 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4253. Min Range: -6.4253
Max Act: 5.9253. Min Act: -0.1700
Data Index: 2628502 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4253. Min Range: -6.4253
Max Act: 5.8941. Min Act: -0.1700
Data Index: 3634708 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4253. Min Range: -6.4253
Max Act: 5.8941. Min Act: -0.1700
Data Index: 7156571 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4253. Min Range: -6.4253
Max Act: 5.8316. Min Act: -0.1700
Data Index: 4847524 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4253. Min Range: -6.4253
Max Act: 5.8628. Min Act: -0.1700
Data Index: 6272469 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4253. Min Range: -6.4253
Max Act: 5.8316. Min Act: -0.1700
Data Index: 8182423 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4253. Min Range: -6.4253
Max Act: 5.8941. Min Act: -0.1700
Data Index: 2230920 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4253. Min Range: -6.4253
Max Act: 5.8316. Min Act: -0.1700
Data Index: 6508627 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4253. Min Range: -6.4253
Max Act: 5.8003. Min Act: -0.1700
Data Index: 3654174 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4253. Min Range: -6.4253
Max Act: 5.8316. Min Act: -0.1700
Data Index: 5905359 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4253. Min Range: -6.4253
Max Act: 5.8316. Min Act: -0.1700
Data Index: 2645053 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4253. Min Range: -6.4253
Max Act: 5.8316. Min Act: -0.1700
Data Index: 4578126 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #19